{"id":"W2115578160","doi":"10.1007/s11263-007-0067-7","title":"Learning to Recognize Objects with Little Supervision","year":2007,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Conditional random field; Pattern recognition (psychology); Computer science; Kernel (algebra); Context (archaeology); Machine learning; Segmentation; Object (grammar); Feature selection; Feature (linguistics); Bayesian probability; Multiple kernel learning; Class (philosophy); Kernel method; Support vector machine; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008313878,0.0001238574,0.0001689337,0.0004419721,0.00005518423,0.0002203112,0.001078733,0.00004337353,0.00001016251],"category_scores_gemma":[0.00008085104,0.00009194279,0.00008259621,0.0003225124,0.00001712083,0.001155255,0.0003229855,0.0002794736,0.00002352131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009043922,"about_ca_system_score_gemma":0.00004979531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000312836,"about_ca_topic_score_gemma":0.000001510935,"domain_scores_codex":[0.9983401,0.00004340899,0.0004242638,0.0002003849,0.000804128,0.0001876629],"domain_scores_gemma":[0.9981021,0.0002083648,0.0002514874,0.0001595018,0.001124044,0.0001544644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002367524,0.00007676292,0.000429072,0.000002654185,0.00003053395,0.0004559679,0.0006627642,0.0004923047,0.005040145,0.0003762688,0.0006355022,0.9915613],"study_design_scores_gemma":[0.006269013,0.03124602,0.07124972,0.003799731,0.00003923279,0.008264289,0.0003331341,0.04122108,0.5208582,0.01525254,0.2996927,0.001774409],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0716069,0.00006072959,0.9262523,0.000769144,0.0007831545,0.00006578015,2.543081e-7,0.00006876899,0.0003929698],"genre_scores_gemma":[0.5712759,0.00003536289,0.4276866,0.0005354913,0.0004047222,2.53083e-7,6.773162e-7,0.000008059808,0.0000528943],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9897869,"threshold_uncertainty_score":0.3749318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009405553709298077,"score_gpt":0.3122572938147168,"score_spread":0.3028517401054188,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}